Skip to main content
Glama
Sign In
cogmem

cogmem

by dcondrey
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to cogmem

  • Codex Memory

    zhangtian-123
    A
    license
    B
    quality
    D
    maintenance
    Local Markdown-backed memory tools for Codex and other MCP-capable agents. Exposes durable agent knowledge via CLI and MCP server.
    5
    MIT

  • Linksee Memory

    michielinksee
    A
    license
    A
    quality
    B
    maintenance
    Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.
    7
    1,548 npm
    16
    MIT

  • repo-memory

    yubinkim444
    A
    license
    A
    quality
    C
    maintenance
    A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep
    5
    75 PyPI
    1
    MIT

Related Servers

  • Projectmem

    riponcm
    A
    license
    A
    quality
    A
    maintenance
    Local-first memory layer for AI coding agents — captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.
    17
    729 PyPI
    876
    MIT

  • memini

    lumayapartners
    A
    license
    A
    quality
    D
    maintenance
    Local-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.
    6
    89 npm
    MIT

  • Sugar Memory

    Renjun22360
    F
    license
    Not graded
    quality
    A
    maintenance
    Provides AI coding agents with a local-first persistent memory layer they can read and write during sessions, storing decisions, preferences, error patterns, and research per project or globally. Enables semantic and keyword search, formatted context recall, and cross-project guideline surfacing without API keys or cloud storage.
    -

  • Sugar

    Benjaminn581
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables AI coding agents to read and write persistent, local-first memory across sessions and projects, with semantic search, global guidelines, and optional autonomous task execution.
    -

  • io.github.cdnsteve/sugar

    Sebastien94506
    F
    license
    Not graded
    quality
    A
    maintenance
    Gives AI coding agents persistent, local-first memory so they can store, semantically search, and recall decisions, preferences, error patterns, and cross-project guidelines directly during a session. It also optionally queues tasks for autonomous execution against that same memory.
    -

  • MegaBrain

    dougrn
    A
    license
    A
    quality
    C
    maintenance
    Enables AI coding assistants to share persistent local memory across sessions and agents, so rules, mandatory specs, verified code snippets, and past mistakes are automatically surfaced before code is generated. It also lets agents log repeated failures as recurrence-counted 'vaccines', preventing the same errors from recurring across Claude, VS Code agents, and local LLMs.
    7
    2
    MIT
Deploy Server
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

A4.6/5.0

Scored across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: note saves memories, recall retrieves them, progress summarizes project state, receipt provides cryptographic proofs, review_pending lists pending rules, status reports system health, tree_head returns the Merkle root, and verify performs deep audit. No overlapping functionality.

Naming Consistency5/5

All tool names are lowercase with underscores for compounds (e.g., review_pending, tree_head). They follow a consistent pattern of verbs or noun phrases that clearly indicate the action or output, with no style mixing.

Tool Count5/5

With 8 tools, the set is well-scoped for a verifiable memory system. It covers storing, retrieving, verifying, and monitoring without being bloated or too sparse.

Completeness4/5

The tools provide core operations (create, read, verify, audit). Missing explicit update/delete tools is a minor gap, but this aligns with the system's append-only, tamper-evident design. A tool for exact-match retrieval could be useful, but semantic recall covers most needs.

Maintenance

ActivityStale
ResponsivenessNo recent community issues

Resources